Figma canvas with a Pickup UI Guidelines prompt beside button, icon and logo components
Figma canvas with a Pickup UI Guidelines prompt beside button, icon and logo components
+ AI News

Figma defines how AI agents work on its platform and opens code layers in beta

Figma Specs gives agents shared design instructions. Code layers enters open beta, letting teams test those instructions in interactive prototypes.

Figma is giving teams a shared place to tell AI agents how their products should look and work. At its first Config event in India, the company introduced Figma Specs, a Markdown-based editor for design instructions, and opened code layers to public beta, TechCrunch reports.

Together, the tools let teams put written requirements beside designs and ask an agent to build interactive prototypes on the canvas. Teams still need to judge whether the result follows those requirements.

Specs puts instructions beside the design

According to Figma’s launch post, a spec can contain shared decisions and references to frames, diagrams and code layers. Teams can import an existing Markdown file by dragging it onto the canvas. Specs is rolling out in open beta to paid plans on web, desktop and mobile.

The document also gives people and agents a common place to discuss changes. Figma’s agent can read and reply to comments. Through Figma’s Model Context Protocol server, a team can pass a spec and its linked context to an external coding agent.

For designers, that means an instruction can sit beside the component it describes. For developers, the handoff can include both the written requirement and the relevant Figma references.

Code layers makes the prototype interactive

Code layers adds working code to designs on the canvas. TechCrunch reports that the feature entered private beta in June and is now in open beta. Users can ask the agent to convert a design into code or edit part of the code to change a prototype.

Figma’s Specs post describes a way back to design review, too. Teams can extract a screen, state or flow from a code layer into editable design layers, then keep those frames beside the spec for review with engineers.

Sources

The AI Feed Desk

The AI Feed Desk

Editorial desk

The AI Feed Desk tracks AI provider updates, model releases, agent tooling, and enterprise adoption, turning fast-moving announcements into source-linked context for builders and operators.

Noticed a typo, incorrect information, or translation error?

Tell us so we can fix it.

Help Improve This Article

Related Articles

An MCP agent test bench replays clean, faulted, and mitigated tool responses

AgentCheck tests whether MCP agents fail safely

A July 13 paper introduces AgentCheck, an MCP workbench for replaying tool faults and confirming whether agent mitigations actually fix them.

The AI Feed Desk

By The AI Feed Desk

Laptop screen showing four Airbnb homes compared side by side with AI summaries beside a Paris map

Airbnb adds AI search and social features as Chesky calls for an agent operating system

Airbnb adds natural-language search and home comparisons. Chesky's agent vision raises a separate test: preserving the booking tools travelers need.

The AI Feed Desk

By The AI Feed Desk

A closed boundary separates a shopping assistant symbol from a checkout terminal; illustration

Amazon blocks Meta's Muse shopping agent from buying on its site

Amazon says Meta's Muse is an unauthorized AI agent, exposing the access and order-recovery rules that shopping agents need beyond product browsing.

The AI Feed Desk

By The AI Feed Desk

Scatter chart comparing decision index scores and median latency for Clef, Clef-flash, Jev and other decision models

Amazon and Cloudflare release open decision models as the Jev clones multiply

AWS releases Strands Decider 2B. Cloudflare adds Clef and Clef-flash, with open weights and hands-on fine-tuning. Task scores show where speed costs accuracy.

The AI Feed Desk

By The AI Feed Desk

White Ambi name and logo on a textured green background

Ex-Plaud executive raises $26M for Ambi, an AI app that listens in the background

Ambi launches iPhone, Mac and Apple Watch apps for ambient capture. Its promise of help during meetings raises a test of whether all-day listening adds value.

The AI Feed Desk

By The AI Feed Desk